def test_compare(self):
for X in [self.Xtrain1, self.Xtrain2]:
for Y in [self.Ytrain1, self.Ytrain2]:
#No bias
greedy_rls = GreedyRLS(X,
Y,
subsetsize=10,
regparam=12,
bias=0.)
selected = greedy_rls.selected
s_complement = list(
set(range(X.shape[1])).difference(selected))
X_cut = X[:, selected]
rls = RLS(X_cut, Y, regparam=12., bias=0.)
W = greedy_rls.predictor.W[selected]
W2 = rls.predictor.W
assert_allclose(W, W2)
assert_array_equal(greedy_rls.predictor.W[s_complement], 0)
assert_array_equal(greedy_rls.predictor.b, 0)
#Bias
greedy_rls = GreedyRLS(X,
Y,
subsetsize=10,
regparam=12,
bias=2.)
selected = greedy_rls.selected
X_cut = X[:, selected]
rls = RLS(X_cut, Y, regparam=12., bias=2.)
W = greedy_rls.predictor.W[selected]
W2 = rls.predictor.W
assert_allclose(W, W2)
assert_allclose(greedy_rls.predictor.b, rls.predictor.b)
def speedtest():
tsize, fsize = 3000, 3000
desiredfcount = 5
Xtrain = mat(random.rand(fsize, tsize), dtype=float64)
bias = 2.
rp = 1.
ylen = 2
Y = mat(random.rand(tsize, ylen), dtype=float64)
rpool = {}
class TestCallback(object):
def callback(self, learner):
print('round')
def finished(self, learner):
pass
tcb = TestCallback()
rpool['callback'] = tcb
rpool['X'] = Xtrain.T
rpool['Y'] = Y
rpool['subsetsize'] = str(desiredfcount)
rpool['regparam'] = rp
rpool['bias'] = bias
grls = GreedyRLS(**rpool)
print(grls.selected)
print(grls.A[grls.selected])
print(grls.b)
def train_rls():
X_train, Y_train, X_test, Y_test = load_housing()
#we select 5 features
learner = GreedyRLS(X_train, Y_train, 5)
#Test set predictions
P_test = learner.predict(X_test)
print("test error %f" %sqerror(Y_test, P_test))
print("Selected features " +str(learner.selected))
def train_rls():
X_train, Y_train, X_test, Y_test = load_housing()
cb = Callback(X_test, Y_test)
learner = GreedyRLS(X_train, Y_train, 13, callbackfun=cb)
#Test set predictions
P_test = learner.predict(X_test)
print("test error %f" % sqerror(Y_test, P_test))
print("Selected features " + str(learner.selected))
def core_greedyrls(X, y, regparam, scount):
cb = Callback()
learner = GreedyRLS(X,
y,
scount,
regparam=regparam,
callbackfun=cb,
bias=0.)
selected = learner.selected
return selected
def train_rls():
mndata = MNIST("./data")
X_train, Y_train = mndata.load_training()
X_test, Y_test = mndata.load_testing()
X_train, X_test = np.array(X_train), np.array(X_test)
#One-vs-all mapping
Y_train = ova(Y_train)
Y_test = ova(Y_test)
#Train greedy RLS, select 10 features
cb = Callback(X_test, Y_test)
learner = GreedyRLS(X_train, Y_train, 50, callbackfun=cb)
print("Selected features " + str(learner.selected))
def train_rls():
#Trains RLS with default parameters (regparam=1.0, kernel='LinearKernel')
X_train, Y_train, X_test, Y_test = load_housing()
learner = GreedyRLS(X_train, Y_train, 5)
#This is how we make predictions
P_test = learner.predict(X_test)
#We can separate the predictor from learner
predictor = learner.predictor
#And do the same predictions
P_test = predictor.predict(X_test)
#Let's get the coefficients of the predictor
w = predictor.W
b = predictor.b
print("number of coefficients %d" % len(w))
print("w-coefficients " + str(w))
print("bias term %f" % b)
def testRLS(self):
print("\n\n\n\nTesting the correctness of the GreedyRLS module.\n\n")
tsize, fsize = 10, 30
desiredfcount = 5
Xtrain = mat(random.rand(fsize, tsize), dtype=float64)
bias = 2.
bias_slice = sqrt(bias) * mat(ones(
(1, Xtrain.shape[1]), dtype=float64))
Xtrain_biased = vstack([Xtrain, bias_slice])
ylen = 2
Y = mat(random.rand(tsize, ylen), dtype=float64)
selected = []
rp = 1.
currentfcount = 0
while currentfcount < desiredfcount:
selected_plus_bias = selected + [fsize]
bestlooperf = 9999999999.
for ci in range(fsize):
if ci in selected_plus_bias: continue
updK = Xtrain_biased[selected_plus_bias +
[ci]].T * Xtrain_biased[selected_plus_bias
+ [ci]]
looperf = 0.
for hi in range(tsize):
hoinds = list(range(0, hi)) + list(range(hi + 1, tsize))
updcutK = updK[ix_(hoinds, hoinds)]
updcrossK = updK[ix_([hi], hoinds)]
loopred = updcrossK * la.inv(
updcutK + rp * mat(eye(tsize - 1))) * Y[hoinds]
looperf += mean(
multiply((loopred - Y[hi]), (loopred - Y[hi])))
if looperf < bestlooperf:
bestcind = ci
bestlooperf = looperf
print('Tester ', ci, looperf)
selected.append(bestcind)
print('Tester ', selected)
currentfcount += 1
selected_plus_bias = selected + [fsize]
K = Xtrain_biased[selected_plus_bias].T * Xtrain_biased[
selected_plus_bias]
G = la.inv(K + rp * mat(eye(tsize)))
A = Xtrain_biased[selected_plus_bias] * G * Y
print('Tester ', A)
rpool = {}
class TestCallback(object):
def callback(self, learner):
print('GreedyRLS', learner.looperf.T)
pass
def finished(self, learner):
pass
tcb = TestCallback()
rpool['callback'] = tcb
rpool['X'] = Xtrain.T
rpool['Y'] = Y
rpool['subsetsize'] = desiredfcount
rpool['regparam'] = rp
rpool['bias'] = bias
grls = GreedyRLS(**rpool)
assert_array_equal(selected, grls.selected)
assert_allclose(A[:-1], grls.A[selected])
assert_allclose(np.sqrt(bias) * A[-1], grls.b)
